© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245657
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     punctuation
    0.38
    జయ
    0.36
     punct
    0.36
     जानेंगे
    0.33
     lectores
    0.33
    [&
    0.33
     lightness
    0.32
     run
    0.32
     пунк
    0.32
    run
    0.31
    POSITIVE LOGITS
    ْع
    0.36
     Online
    0.35
    <unused92>
    0.35
    Online
    0.34
    hdd
    0.34
    Ĕ
    0.34
     ऑनलाइन
    0.33
    ไม
    0.33
    édi
    0.32
    づ
    0.32
    Activations Density 0.002%

    No Known Activations